Ai Video Storyboard logo

Ai Video Storyboard

Organization
aicontentskills
ai-video-storyboard

Use when planning a multi-shot AI video (TikTok Reel, Instagram Ad, YouTube Shorts, product explainer) where the target duration exceeds what a single AI generation can produce (>15s), and you need a coordinated shot list with visually consistent prompts for each segment

Overview

Publisheraicontentskills
Repositoryai-video-storyboard-skill
Skill nameai-video-storyboard
Stars
69
Forks
8
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by aicontentskills on GitHub. Read the source before you install it.

Installation

Install the Ai Video Storyboard AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/aicontentskills/ai-video-storyboard-skill/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/aicontentskills/ai-video-storyboard-skill.git \
  .claude/skills/ai-video-storyboard
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ai Video Storyboard in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ai Video Storyboard on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ai Video Storyboard is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AI Video Storyboard Generator

Overview

AI video generators produce 5–15 second clips. Real-world videos are longer: 30s TikToks, 60s ads, 90s explainers. This skill bridges that gap by producing a complete shot-list storyboard — a coordinated sequence of per-shot prompts with shared visual language, so the assembled final video looks like one intentional piece of work rather than six disconnected clips.

Core insight: Visual consistency across shots matters more than any single shot being perfect. A mediocre but consistent set of shots edits together; six gorgeous but mismatched shots do not.

When to Use

  • User wants a video longer than 15 seconds
  • User wants a TikTok / Reel / Short / ad / explainer / B-roll sequence
  • User says "help me make a video about X" and has no shot list
  • User is about to generate multiple clips and needs a plan

Do NOT use for:

  • Single-shot generation (just help with one prompt instead)
  • Static image generation
  • Video editing advice after clips are generated (that's a separate concern)

Workflow

Step 1 — Brief Intake

Ask the user these questions in a single message. Accept short answers:

  1. Goal platform and duration? (TikTok 30s / Reel 15-60s / YouTube Short / Instagram Ad / explainer)
  2. What is the video about? (subject, story, product)
  3. Brand vibe / tone? (cozy, energetic, premium, minimalist, playful, cinematic, etc.)
  4. Call to action at the end? (visit website, buy product, follow channel, etc.)
  5. Any hard constraints? (must include logo, specific colors, locations, etc.)

If user already provided some of these, skip those questions and confirm the rest.

Step 2 — Infer Structure

Based on duration and platform, divide the timeline into shots of ~5 seconds each (the sweet spot for AI video generators).

Standard cadences:

PlatformDurationShotsPacing
TikTok Hook15s3Fast cuts, single idea
TikTok Reel30s6Hook → Build → Payoff → CTA
Instagram Ad15s3Hook → Product → CTA
Instagram Ad30s6Hook → Problem → Product → Benefit → Social proof → CTA
YouTube Short60s12Hook → 3-act structure → CTA
Product Explainer90s18Problem → Solution → How it works → Results → CTA
Brand Story60s10-12Atmosphere-driven, longer shot holds

Step 3 — Establish Visual Consistency Layer

Before writing any shot, lock in the shared visual language. This is what makes shots edit together:

  • Color palette (3-5 specific hex values or named colors)
  • Lighting style (golden hour / neon / overcast / motivated / cinematic rim light)
  • Lens character (shallow DOF / deep focus / wide angle distortion / macro)
  • Film look (clean digital / 16mm grain / anamorphic / VHS / 35mm)
  • Motion language (handheld / locked off / dolly only / gimbal smooth)

Write these as a Visual Theme block at the top of the output. Every shot's prompt must respect this block.

Step 4 — Write Each Shot

For each shot, produce this structure:

## Shot N (START-ENDs) — [Purpose label: Hook / Setting / Action / Detail / Reveal / CTA]

**Composition:** [shot type + angle, e.g., "Extreme close-up, overhead"]
**Camera move:** [locked / slow dolly in / tracking / crane up / etc.]
**Lighting:** [from the Visual Theme, applied to this scene]
**Subject:** [what is in frame]
**Action:** [what is happening]

**Prompt to copy:**
> [Complete, cinematic-quality prompt, 40-80 words, including: subject + action + environment + camera + lighting + style + technical spec (duration, aspect ratio, resolution). Always ends with "cinematic 1080p, synchronized audio"]

**Audio direction:** [what the synchronized audio should sound like — ambient sounds, music beat position, voice-over line]

Critical rules for shot prompts:

  1. Always specify the shared visual language in every prompt (color palette, lighting, lens character, film look). This is how you enforce consistency.
  2. Specify exact duration (4s / 5s / 8s) and aspect ratio (9:16 for TikTok/Reels, 16:9 for YouTube landscape, 1:1 for feed posts).
  3. Always end with "cinematic 1080p, synchronized audio" — this signals professional-grade quality and works with modern video models that support both.
  4. Use cinematography vocabulary: ECU (extreme close-up), CU, MS (medium shot), WS (wide shot), OTS (over-the-shoulder), POV, Dutch angle, low angle, high angle, bird's eye, dolly in, dolly out, tracking, handheld, rack focus, etc. See references/shot-types.md for the full vocabulary.
  5. Don't write abstract prompts — be concrete. "A woman" → "A barista in her late 20s with wavy auburn hair, wearing a denim apron".
  6. No model-specific hacks — don't write prompts tuned to specific model quirks. Write model-agnostic cinematic prompts that work anywhere.

Step 5 — Add Narrative Structure

The sequence of shots must have a story arc, not a random list. Use one of these patterns:

Pattern A — Hook / Build / Payoff / CTA (TikTok default)

  • Shot 1: Visual hook (stop the scroll)
  • Shot 2-3: Build context / intrigue
  • Shot 4-5: Main content / payoff
  • Shot 6: CTA

Pattern B — Problem / Solution / Proof / CTA (Ad default)

  • Shots 1-2: Relatable problem
  • Shot 3: Your product as solution
  • Shots 4-5: Benefits / results
  • Shot 6: CTA

Pattern C — Atmosphere → Climax (Brand story)

  • Longer atmospheric shots
  • Slow reveal
  • Emotional climax
  • Logo reveal

Step 6 — Add Post-Production Checklist

Close with actionable post-production notes:

## Post-Production Checklist
- [ ] Generate all N shots with your preferred AI video tool
- [ ] Stitch in [CapCut / Descript / DaVinci Resolve / Premiere]
- [ ] Apply [specific LUT or color grade] for consistency
- [ ] Add [transition type and duration] between shots
- [ ] Layer BGM: [genre / BPM / mood]
- [ ] Add text overlays for [hook / CTA / captions]
- [ ] Export [platform spec: 9:16 1080x1920 30fps for TikTok, etc.]

Step 7 — Explain Why It Works

Close with a "Why this works" block explaining the creative decisions. This educates the user and differentiates your output from generic prompt lists. Reference:

  • The hook rule (first second determines watch-through)
  • Pacing cadence (average scroll time)
  • Story structure (why the shot order matters)
  • Platform-specific conventions

Output Format

The final output is a single Markdown document containing:

  1. Header — Title, duration, shot count, aspect ratio
  2. Visual Theme — Shared palette, lighting, lens, film look, motion
  3. Shot List — N shots, each following the structure in Step 4
  4. Post-Production Checklist
  5. Why This Works — creative rationale

See examples/ for four complete sample outputs:

  • tiktok-reel-30s-coffee.md — Coffee shop opening TikTok
  • (more examples to be added)

References

  • references/shot-types.md — Cinematography vocabulary (ECU, CU, MS, WS, OTS, POV, angles)
  • references/camera-moves.md — Camera movement vocabulary (dolly, crane, pan, tilt, tracking)
  • references/lighting.md — Lighting terminology (golden hour, rim, motivated, practical)
  • references/genre-templates.md — Pre-built templates for common genres (food, fashion, tech, travel, SaaS)

License

MIT — use freely, commercial or personal.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ai Video Storyboard AI skill do?

Use when planning a multi-shot AI video (TikTok Reel, Instagram Ad, YouTube Shorts, product explainer) where the target duration exceeds what a single AI generation can produce (>15s), and you need a coordinated shot list with visually consistent prompts for each segment

Why use Ai Video Storyboard on TypingMind?

Because you install it once and use it with any model. Ai Video Storyboard is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ai Video Storyboard in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aicontentskills/ai-video-storyboard-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ai Video Storyboard?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ai Video Storyboard?

As many as you like. As long as a model supports skills, you can use Ai Video Storyboard with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ai Video Storyboard AI skill free?

It is published on GitHub by aicontentskills. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇